Catalunya 2022

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful behavioral detail: the return includes hierarchy with slugs and a formal citation with DOI. No side effects are mentioned, consistent with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, each earning its place: first defines the action and scope, second details the outputs and connection to get_section. No wasted words or information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description need not detail return fields. The description provides enough high-level context (hierarchy, slugs, DOI) and references sibling tools for navigation. An agent can fully understand the tool's role.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%; the locale parameter is fully documented in the schema. The description adds no additional parameter guidance, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the complete structure of a specific policy document, including counts (3 spheres, 12 goals, 91 actions). It distinguishes itself from sibling 'get_section' by mentioning that canonical slugs are provided for navigation via that tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (to get full document hierarchy) versus alternatives like get_section (for navigation via slugs). It does not explicitly state exclusions, but the context is clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it is a safe read. The description adds valuable context by explaining the slug pattern and static pages, which helps the agent understand the tool's input constraints. It does not describe error handling, but the annotation coverage lowers the burden, and the description contributes meaningful beyond-annotation information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, each earning its place: purpose, slug pattern, static pages, and a pointer to metadata. It is front-loaded with the primary action and contains no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With two parameters, no output schema, and a simple read operation, the description covers the essential aspects: what it retrieves, how to format the slug, and where to get valid slugs. It could optionally mention the return format (e.g., plain text vs. markdown), but given the tool's simplicity and annotation coverage, it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. Both parameters (slug and locale) are fully described in the schema, including pattern, enum, and default. The description provides concrete slug examples, but these are illustrative rather than adding new semantic meaning not already in the schema. Therefore, it meets the baseline but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Retrieve the full text of any section of the Catalunya 2022 document by its canonical slug.' It clearly differentiates from siblings by focusing on full-text retrieval by slug, and it mentions the sibling get_document_metadata for discovering slugs, setting it apart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly directs users to 'Use get_document_metadata to discover all available slugs,' which serves as a when-to-use pointer for a sibling tool. While it does not directly compare with search_document or list_proposals, the tool's narrow purpose makes usage clear. There is no misleading guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so no contradiction. The description adds value by stating it returns a fixed set (all 91 proposals) and lists returned fields, which is consistent with annotations. It doesn't mention pagination or rate limits, but given the limited scope and annotations, the description is sufficiently transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first states what the tool does with scope and optional filters, the second explains outputs and next steps. Every sentence is earned and front-loaded with key information. No redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists to document return values, the description covers the essential: scope, filters, returned fields, and usage pattern with sibling tool. The low parameter count (3), no required parameters, and rich annotations make this complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by linking the parameters to the specific document context ('Catalunya 2022 document') and explaining the purpose of the returned slug for use with get_section. The locale parameter is well-described in the schema with clear enum values, so the description's additional context on the default is helpful but not essential.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all 91 action proposals from a specific document (Catalunya 2022), with optional filtering by sphere or goal. The verb 'list' and resource 'action proposals' are specific, and the description distinguishes it from siblings like get_section (for reading full content) and search_document (for searching).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly guides when to use this tool (to list proposals) and what to do next ('Use get_section with the returned slug to read full action content'), effectively differentiating from the sibling get_section tool. It also specifies the optional filters sphereId and goalId, providing clear context for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint as false, so the description correctly aligns with a safe, read-only search. Beyond annotations, the description adds valuable behavioral details: returns up to 10 results, independent term matching with coverage-based ranking, exact phrase matching for quotes, and automatic diacritic handling. This adds significant depth beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two well-structured sentences, front-loads the core purpose, and each sentence adds critical information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (not shown to us but present) and detailed annotations, the description covers all needed aspects: search behavior, limits, follow-up integration, language nuances, and scope definitions. No gaps are apparent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds meaning beyond schema: it clarifies the scope values (e.g., '90 proposals' for 'action') and provides usage tips for locale (original language is Catalan). The description also explains the query behavior (independent term matching, phrase quotes) which is not in the schema. This adds enough value to bring the score to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('search'), resource ('Catalunya 2022 - RESET policy document'), and method ('by keyword'). It distinguishes this tool from siblings by mentioning follow-up with 'get_section' and return of 'canonical slugs', which is unique among the listed siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use this tool (to search the document by keyword) and what to use for follow-up ('get_section' is named). It also provides guidance on how to use it effectively, including tips about quoted phrases for exact matches and diacritic handling. It does not mention alternatives like 'list_proposals' but clearly positions this for searching rather than listing all content.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.